AI-Assisted ECG Model Speeds Up ACS Detection Across India: Real-World Study
India: A recent study published in Cureus highlights the role of artificial intelligence (AI) in improving the early detection of acute coronary syndrome (ACS) in India. Conducted by Praveen Chandra from Medanta - The Medicity and colleagues, the study evaluated an AI-assisted hub-and-spoke model designed to enhance electrocardiogram (ECG) interpretation and reduce diagnostic delays.
ACS continues to be a major contributor to morbidity and mortality in India, often worsened by delays in diagnosis and treatment. To address this, the “Heart Beat” project was implemented across multiple healthcare settings. This model connected primary healthcare centers (spokes) with advanced cardiac hospitals (hubs) equipped with catheterization laboratories, enabling rapid transmission and centralized interpretation of ECG data using AI.
The study analyzed retrospective, real-world data collected between January 2020 and December 2022. A total of 45,488 ECGs were recorded from 66 spoke centers linked to 10 hub hospitals across six Indian states. AI-enabled 12-lead ECGs performed at the spokes were categorized into six groups: Normal, Abnormal, Borderline, Critical, Otherwise Normal, and Pacemaker.
The study led to the following findings:
- 50.53% of ECGs were classified as normal, 42.64% as abnormal, and 6.58% as critical.
- Most cardiovascular conditions were identified in abnormal and critical ECG categories.
- Left ventricular hypertrophy was the most commonly detected condition, seen in 8.78% of patients.
- ST-elevation myocardial infarction (STEMI) was more frequently observed, with 231 cases (0.51%).
- Non-ST-elevation myocardial infarction (NSTEMI) was comparatively rare, identified in 22 cases (0.05%).
- The higher prevalence of STEMI highlights the need for rapid diagnosis and timely intervention.
- The overall mean turnaround time (TAT) for ECG acquisition and diagnosis using AI was 5.12 minutes.
- Critical ECGs were identified faster, with a mean TAT of 2.91 minutes.
- The observed TAT is significantly below the recommended 10-minute benchmark for timely ECG evaluation in suspected ACS cases.
These findings suggest that AI-assisted ECG analysis can accelerate diagnosis, enabling quicker triage and management of patients. The model also supports efficient resource utilization, particularly in settings with limited access to specialized cardiac care.
However, the authors note that the study is observational and does not assess long-term clinical outcomes. Further research is needed to determine whether faster diagnosis translates into improved survival, better treatment adherence, and enhanced quality of life. Future studies comparing AI interpretations with cardiologist assessments will also be important to validate diagnostic accuracy.
Overall, the study demonstrates that an AI-enabled hub-and-spoke model can significantly improve the speed and efficiency of ACS diagnosis, with potential to enhance cardiac care delivery across diverse healthcare settings in India.
Reference:
Chandra P, Batra A, Singh A K, et al. (March 01, 2026) Artificial Intelligence-Assisted ECG in a Hub-and-Spoke Network in India: Real-World Performance in Acute Coronary Syndrome Detection and Diagnostic Turnaround Times. Cureus 18(3): e104518. DOI 10.7759/cureus.104518
Next Story